{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b02n_zJ_hl3d"
      },
      "source": [
        "## Cookbook for using Hugging Face Hub with Embedchain"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gyJ6ui2vhtMY"
      },
      "source": [
        "### Step-1: Install embedchain package"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "-NbXjAdlh0vJ",
        "outputId": "35ddc904-8067-44cf-dcc9-3c8b4cd29989"
      },
      "outputs": [],
      "source": [
        "!pip install embedchain[huggingface_hub,opensource]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nGnpSYAAh2bQ"
      },
      "source": [
        "### Step-2: Set Hugging Face Hub related environment variables\n",
        "\n",
        "You can find your `HUGGINGFACE_ACCESS_TOKEN` key on your [Hugging Face Hub dashboard](https://huggingface.co/settings/tokens)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "0fBdQ9GAiRvK"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "from embedchain import App\n",
        "\n",
        "os.environ[\"HUGGINGFACE_ACCESS_TOKEN\"] = \"hf_xxx\""
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "PGt6uPLIi1CS"
      },
      "source": [
        "### Step-3 Create embedchain app and define your config"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Amzxk3m-i3tD"
      },
      "outputs": [],
      "source": [
        "app = App.from_config(config={\n",
        "    \"llm\": {\n",
        "        \"provider\": \"huggingface\",\n",
        "        \"config\": {\n",
        "            \"model\": \"google/flan-t5-xxl\",\n",
        "            \"temperature\": 0.5,\n",
        "            \"max_tokens\": 1000,\n",
        "            \"top_p\": 0.8,\n",
        "            \"stream\": False\n",
        "        }\n",
        "    },\n",
        "    \"embedder\": {\n",
        "        \"provider\": \"huggingface\",\n",
        "        \"config\": {\n",
        "            \"model\": \"sentence-transformers/all-mpnet-base-v2\"\n",
        "        }\n",
        "    }\n",
        "})"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XNXv4yZwi7ef"
      },
      "source": [
        "### Step-4: Add data sources to your app"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "id": "Sn_0rx9QjIY9",
        "outputId": "3c2a803a-3a93-4b0d-a6ae-17ae3c96c3c2"
      },
      "outputs": [],
      "source": [
        "app.add(\"https://www.forbes.com/profile/elon-musk\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_7W6fDeAjMAP"
      },
      "source": [
        "### Step-5: All set. Now start asking questions related to your data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cvIK7dWRjN_f",
        "outputId": "47a89d1c-b322-495c-822a-6c2ecef894d2"
      },
      "outputs": [],
      "source": [
        "while(True):\n",
        "    question = input(\"Enter question: \")\n",
        "    if question in ['q', 'exit', 'quit']:\n",
        "        break\n",
        "    answer = app.query(question)\n",
        "    print(answer)"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}